Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 639691872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d15ba72f4dc69f9dcbb5f758712ea2980cb6b088f5ee08d0de698192aaf6f335
|
3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1279641042
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:621644a9815638dfd95caa71bb08d0784fa5bc52c0170e5b66d537719517f69d
|
3 |
size 1279641042
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:060cba38fe66b80f028a2e75db1ce281df2d6087ce6ce7301de8f58db0321887
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -373,6 +373,364 @@
|
|
373 |
"eval_samples_per_second": 11.764,
|
374 |
"eval_steps_per_second": 5.882,
|
375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
376 |
}
|
377 |
],
|
378 |
"logging_steps": 1,
|
@@ -396,12 +754,12 @@
|
|
396 |
"should_evaluate": false,
|
397 |
"should_log": false,
|
398 |
"should_save": true,
|
399 |
-
"should_training_stop":
|
400 |
},
|
401 |
"attributes": {}
|
402 |
}
|
403 |
},
|
404 |
-
"total_flos":
|
405 |
"train_batch_size": 8,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1233247518539429,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.3436426116838488,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
373 |
"eval_samples_per_second": 11.764,
|
374 |
"eval_steps_per_second": 5.882,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.17525773195876287,
|
379 |
+
"grad_norm": 0.7763431072235107,
|
380 |
+
"learning_rate": 7.938926261462366e-05,
|
381 |
+
"loss": 1.1863,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.17869415807560138,
|
386 |
+
"grad_norm": 0.6419703960418701,
|
387 |
+
"learning_rate": 7.754484907260513e-05,
|
388 |
+
"loss": 1.2078,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.18213058419243985,
|
393 |
+
"grad_norm": 0.4610435366630554,
|
394 |
+
"learning_rate": 7.564496387029532e-05,
|
395 |
+
"loss": 1.1107,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18556701030927836,
|
400 |
+
"grad_norm": 0.31423109769821167,
|
401 |
+
"learning_rate": 7.369343312364993e-05,
|
402 |
+
"loss": 1.0897,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18900343642611683,
|
407 |
+
"grad_norm": 0.22052399814128876,
|
408 |
+
"learning_rate": 7.169418695587791e-05,
|
409 |
+
"loss": 1.0426,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.19243986254295534,
|
414 |
+
"grad_norm": 0.18192903697490692,
|
415 |
+
"learning_rate": 6.965125158269619e-05,
|
416 |
+
"loss": 1.0934,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.1958762886597938,
|
421 |
+
"grad_norm": 0.186998650431633,
|
422 |
+
"learning_rate": 6.756874120406714e-05,
|
423 |
+
"loss": 1.159,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19931271477663232,
|
428 |
+
"grad_norm": 0.19652201235294342,
|
429 |
+
"learning_rate": 6.545084971874738e-05,
|
430 |
+
"loss": 1.0594,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.2027491408934708,
|
435 |
+
"grad_norm": 0.21376550197601318,
|
436 |
+
"learning_rate": 6.330184227833376e-05,
|
437 |
+
"loss": 1.08,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20618556701030927,
|
442 |
+
"grad_norm": 0.20765534043312073,
|
443 |
+
"learning_rate": 6.112604669781572e-05,
|
444 |
+
"loss": 0.9949,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.20962199312714777,
|
449 |
+
"grad_norm": 0.2084871083498001,
|
450 |
+
"learning_rate": 5.8927844739931834e-05,
|
451 |
+
"loss": 1.0845,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.21305841924398625,
|
456 |
+
"grad_norm": 0.20915870368480682,
|
457 |
+
"learning_rate": 5.6711663290882776e-05,
|
458 |
+
"loss": 1.0677,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21649484536082475,
|
463 |
+
"grad_norm": 0.19567368924617767,
|
464 |
+
"learning_rate": 5.448196544517168e-05,
|
465 |
+
"loss": 1.0483,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21993127147766323,
|
470 |
+
"grad_norm": 0.2006818801164627,
|
471 |
+
"learning_rate": 5.2243241517525754e-05,
|
472 |
+
"loss": 1.1014,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.22336769759450173,
|
477 |
+
"grad_norm": 0.1980873942375183,
|
478 |
+
"learning_rate": 5e-05,
|
479 |
+
"loss": 1.0755,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2268041237113402,
|
484 |
+
"grad_norm": 0.1960572451353073,
|
485 |
+
"learning_rate": 4.775675848247427e-05,
|
486 |
+
"loss": 1.0844,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.23024054982817868,
|
491 |
+
"grad_norm": 0.18849298357963562,
|
492 |
+
"learning_rate": 4.551803455482833e-05,
|
493 |
+
"loss": 1.0507,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.23367697594501718,
|
498 |
+
"grad_norm": 0.19031502306461334,
|
499 |
+
"learning_rate": 4.328833670911724e-05,
|
500 |
+
"loss": 1.0865,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.23711340206185566,
|
505 |
+
"grad_norm": 0.1852409988641739,
|
506 |
+
"learning_rate": 4.107215526006817e-05,
|
507 |
+
"loss": 1.0678,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.24054982817869416,
|
512 |
+
"grad_norm": 0.1880156397819519,
|
513 |
+
"learning_rate": 3.887395330218429e-05,
|
514 |
+
"loss": 1.1267,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.24398625429553264,
|
519 |
+
"grad_norm": 0.190456360578537,
|
520 |
+
"learning_rate": 3.6698157721666246e-05,
|
521 |
+
"loss": 1.1162,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24742268041237114,
|
526 |
+
"grad_norm": 0.18321743607521057,
|
527 |
+
"learning_rate": 3.4549150281252636e-05,
|
528 |
+
"loss": 1.1242,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.2508591065292096,
|
533 |
+
"grad_norm": 0.2000783532857895,
|
534 |
+
"learning_rate": 3.243125879593286e-05,
|
535 |
+
"loss": 1.1294,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.2542955326460481,
|
540 |
+
"grad_norm": 0.21174149215221405,
|
541 |
+
"learning_rate": 3.0348748417303823e-05,
|
542 |
+
"loss": 1.1342,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25773195876288657,
|
547 |
+
"grad_norm": 0.19860917329788208,
|
548 |
+
"learning_rate": 2.8305813044122097e-05,
|
549 |
+
"loss": 1.1456,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.2611683848797251,
|
554 |
+
"grad_norm": 0.20266704261302948,
|
555 |
+
"learning_rate": 2.630656687635007e-05,
|
556 |
+
"loss": 1.1071,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2646048109965636,
|
561 |
+
"grad_norm": 0.20789256691932678,
|
562 |
+
"learning_rate": 2.43550361297047e-05,
|
563 |
+
"loss": 1.0829,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.26804123711340205,
|
568 |
+
"grad_norm": 0.20565740764141083,
|
569 |
+
"learning_rate": 2.245515092739488e-05,
|
570 |
+
"loss": 1.1548,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.27147766323024053,
|
575 |
+
"grad_norm": 0.2065347284078598,
|
576 |
+
"learning_rate": 2.061073738537635e-05,
|
577 |
+
"loss": 1.0775,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.27491408934707906,
|
582 |
+
"grad_norm": 0.20886455476284027,
|
583 |
+
"learning_rate": 1.8825509907063327e-05,
|
584 |
+
"loss": 1.1291,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.27835051546391754,
|
589 |
+
"grad_norm": 0.2221737802028656,
|
590 |
+
"learning_rate": 1.7103063703014372e-05,
|
591 |
+
"loss": 1.1161,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.281786941580756,
|
596 |
+
"grad_norm": 0.2226671576499939,
|
597 |
+
"learning_rate": 1.544686755065677e-05,
|
598 |
+
"loss": 1.1343,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.2852233676975945,
|
603 |
+
"grad_norm": 0.23488934338092804,
|
604 |
+
"learning_rate": 1.3860256808630428e-05,
|
605 |
+
"loss": 1.1316,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.28865979381443296,
|
610 |
+
"grad_norm": 0.22793255746364594,
|
611 |
+
"learning_rate": 1.2346426699819458e-05,
|
612 |
+
"loss": 1.1914,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.2920962199312715,
|
617 |
+
"grad_norm": 0.21478554606437683,
|
618 |
+
"learning_rate": 1.090842587659851e-05,
|
619 |
+
"loss": 1.1428,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.29553264604810997,
|
624 |
+
"grad_norm": 0.23316501080989838,
|
625 |
+
"learning_rate": 9.549150281252633e-06,
|
626 |
+
"loss": 1.1249,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.29896907216494845,
|
631 |
+
"grad_norm": 0.23652265965938568,
|
632 |
+
"learning_rate": 8.271337313934869e-06,
|
633 |
+
"loss": 1.189,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.3024054982817869,
|
638 |
+
"grad_norm": 0.23535004258155823,
|
639 |
+
"learning_rate": 7.077560319906695e-06,
|
640 |
+
"loss": 1.0792,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.30584192439862545,
|
645 |
+
"grad_norm": 0.258597195148468,
|
646 |
+
"learning_rate": 5.9702234071631e-06,
|
647 |
+
"loss": 1.1569,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.30927835051546393,
|
652 |
+
"grad_norm": 0.2510943114757538,
|
653 |
+
"learning_rate": 4.951556604879048e-06,
|
654 |
+
"loss": 1.1356,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.3127147766323024,
|
659 |
+
"grad_norm": 0.2706563472747803,
|
660 |
+
"learning_rate": 4.023611372427471e-06,
|
661 |
+
"loss": 1.1213,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3161512027491409,
|
666 |
+
"grad_norm": 0.27767154574394226,
|
667 |
+
"learning_rate": 3.18825646801314e-06,
|
668 |
+
"loss": 1.1168,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.31958762886597936,
|
673 |
+
"grad_norm": 0.2995973229408264,
|
674 |
+
"learning_rate": 2.4471741852423237e-06,
|
675 |
+
"loss": 1.1346,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3230240549828179,
|
680 |
+
"grad_norm": 0.3433845341205597,
|
681 |
+
"learning_rate": 1.8018569652073381e-06,
|
682 |
+
"loss": 1.1632,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.32646048109965636,
|
687 |
+
"grad_norm": 0.3424028754234314,
|
688 |
+
"learning_rate": 1.2536043909088191e-06,
|
689 |
+
"loss": 1.2433,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.32989690721649484,
|
694 |
+
"grad_norm": 0.3730294704437256,
|
695 |
+
"learning_rate": 8.035205700685167e-07,
|
696 |
+
"loss": 1.1239,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.3333333333333333,
|
701 |
+
"grad_norm": 0.40019187331199646,
|
702 |
+
"learning_rate": 4.52511911603265e-07,
|
703 |
+
"loss": 1.273,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.33676975945017185,
|
708 |
+
"grad_norm": 0.4186374843120575,
|
709 |
+
"learning_rate": 2.012853002380466e-07,
|
710 |
+
"loss": 1.1646,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3402061855670103,
|
715 |
+
"grad_norm": 0.471892386674881,
|
716 |
+
"learning_rate": 5.0346672934270534e-08,
|
717 |
+
"loss": 1.2248,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.3436426116838488,
|
722 |
+
"grad_norm": 0.5741357803344727,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 1.3389,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.3436426116838488,
|
729 |
+
"eval_loss": 1.1233247518539429,
|
730 |
+
"eval_runtime": 41.6622,
|
731 |
+
"eval_samples_per_second": 11.761,
|
732 |
+
"eval_steps_per_second": 5.881,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
754 |
"should_evaluate": false,
|
755 |
"should_log": false,
|
756 |
"should_save": true,
|
757 |
+
"should_training_stop": true
|
758 |
},
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 1.4302829573308416e+17,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|